@@ -1016,7 +1016,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
static unsigned long weighted_cpuload(const int cpu);
static unsigned long source_load(int cpu);
-static unsigned long target_load(int cpu);
+static unsigned long target_load(int cpu, int imbalance_pct);
static unsigned long power_of(int cpu);
static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
@@ -3967,7 +3967,7 @@ static unsigned long source_load(int cpu)
* Return a high guess at the load of a migration-target cpu weighted
* according to the scheduling class and "nice" value.
*/
-static unsigned long target_load(int cpu)
+static unsigned long target_load(int cpu, int imbalance_pct)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
@@ -3975,6 +3975,11 @@ static unsigned long target_load(int cpu)
if (!sched_feat(LB_BIAS))
return total;
+ /*
+ * Bias target load with imbalance_pct.
+ */
+ total = total * imbalance_pct / 100;
+
return max(rq->cpu_load, total);
}
@@ -4190,8 +4195,8 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
this_cpu = smp_processor_id();
prev_cpu = task_cpu(p);
- load = source_load(prev_cpu);
- this_load = target_load(this_cpu);
+ load = weighted_cpuload(prev_cpu);
+ this_load = weighted_cpuload(this_cpu);
/*
* If sync wakeup then subtract the (maximum possible)
@@ -4247,7 +4252,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
if (balanced ||
(this_load <= load &&
- this_load + target_load(prev_cpu) <= tl_per_task)) {
+ this_load + weighted_cpuload(prev_cpu) <= tl_per_task)) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
@@ -4293,7 +4298,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
if (local_group)
load = source_load(i);
else
- load = target_load(i);
+ load = target_load(i, imbalance);
avg_load += load;
}
@@ -4309,7 +4314,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
}
} while (group = group->next, group != sd->groups);
- if (!idlest || 100*this_load < imbalance*min_load)
+ if (!idlest || this_load < min_load)
return NULL;
return idlest;
}
@@ -5745,6 +5750,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
{
unsigned long load;
int i;
+ int bias = 100 + (env->sd->imbalance_pct - 100) / 2;
memset(sgs, 0, sizeof(*sgs));
@@ -5752,8 +5758,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
struct rq *rq = cpu_rq(i);
/* Bias balancing toward cpus of our domain */
- if (local_group)
- load = target_load(i);
+ if (local_group && env->idle != CPU_IDLE)
+ load = target_load(i, bias);
else
load = source_load(i);
@@ -6193,14 +6199,6 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
if ((local->idle_cpus < busiest->idle_cpus) &&
busiest->sum_nr_running <= busiest->group_weight)
goto out_balanced;
- } else {
- /*
- * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
- * imbalance_pct to be conservative.
- */
- if (100 * busiest->avg_load <=
- env->sd->imbalance_pct * local->avg_load)
- goto out_balanced;
}
force_balance:
Old code considers the bias in source/target_load already. but still use imbalance_pct as last check in idlest/busiest group finding. It is also a kind of redundant job. If we bias imbalance in source/target_load, we'd better not use imbalance_pct again. After cpu_load array removed, it is nice time to unify the target bias consideration. So I remove the imbalance_pct from last check and add the live bias using. On wake_affine, since all archs' wake_idx is 0, current logical is just want to prefer current cpu. so we follows this logical. Just renaming the target_load/source_load to wegithed_cpuload for more exact meaning. Thanks for reminding from Morten! Signed-off-by: Alex Shi <alex.shi@linaro.org> --- kernel/sched/fair.c | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-)